© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166612
    Prev
    Next
    INDEX
    Explanations

    foreign characters and specific possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akespe
    0.37
    ฉ
    0.37
     cg
    0.37
     CG
    0.36
     Only
    0.36
    wendungs
    0.36
    ሶ
    0.36
    same
    0.36
    陀
    0.36
    Induced
    0.35
    POSITIVE LOGITS
    㕸
    0.42
    iniu
    0.40
    umpang
    0.38
    رمپ
    0.37
     डिप्ट
    0.36
     напрямую
    0.36
     peł
    0.36
    umbr
    0.36
    ềm
    0.36
    ইহার
    0.35
    Activations Density 0.001%

    No Known Activations